TL;DR
A Multi-Granularity Implicit Temporal (MGIT) framework that enhances temporal representation and reasoning by modeling implicit temporal dependencies across different granularities is proposed, highlighting its effectiveness in capturing implicit temporal information and enhancing multi-granularity temporal reasoning.
The Temporal-Weighted Transfer Network (TWTNET), a novel reasoning model that jointly leverages statistical modeling and historical information transfer, is proposed, which achieves more robust and interpretable extrapolative reasoning.
Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step queries due to single-pass reasoning pipelines. We propose SABET-QA, a framework that iteratively refines reasoning states across multiple hops via a bidirectional entity-temporal scoring mechanism and a slot-aware contextualization module that aligns question semantics with temporal KG embeddings. A differentiable working memory enables progressive hypothesis refinement, while auxiliary temporal boundaries serve as coarse supervision when available. Experiments on CronQuestions, Complex-CronQuestions, MultiTQ, and TimeQuestions demonstrate consistent improvements over strong baselines, particularly on complex multi-step temporal queries.
Given a partially observed Temporal Knowledge Graph (TKG), how can we accurately predict missing entities? Unlike static knowledge graphs, TKGs encode facts within temporal contexts, requiring models to reason over both graph structure and time. However, existing TKGC approaches often sample neighbors solely based on temporal proximity, introducing irrelevant context and noise. Moreover, many methods compress snapshots into latent representations and rely on global sequence encoders for temporal modeling, losing edge-level structure and localized relation-specific patterns. In this paper, we propose TiRano (Tensorized Relation-aware temporal reasoning for knowledge graph completion), an accurate and efficient tensor-based temporal reasoning framework for TKGC. TiRano samples relation-adaptive temporal neighbors to construct compact, query-centric subgraphs, thereby reducing noise and computational overhead. Furthermore, TiRano organizes these subgraphs into structure-preserving, time-aligned snapshot tensors, and applies a relation-conditioned temporal convolution, which effectively captures localized edge-level temporal dynamics. Through extensive experiments, we demonstrate that TiRano consistently outperforms state-of-the-art TKGC methods in terms of both prediction accuracy and efficiency, achieving up to 12.3% higher accuracy and 2.4× faster inference.
FITTER consistently outperforms inductive baselines without retraining, indicating that vocabulary-agnostic structural learning is a viable foundation for inference over the heterogeneous knowledge graphs of the Semantic Web.
This work proposes a multi-granularity knowledge refinement approach to prune historical TKGs, which selectively removes irrelevant edges and unnecessary nodes at both the edge and node levels.